Malaria cell image classification by explainable artificial intelligence

Towards digital diagnosis of malaria: How far have we reached?

The need for precise and early diagnosis of malaria and its distinction from other febrile illnesses is no doubt a prerequisite, primarily when standard rapid diagnostic tests (RDTs) cannot be totally relied upon. At the time of disease outbreaks, the pressure on hospital staff remains high and the chances of human error increase. Therefore, in the era of digitalisation of medicine as well as diagnostic approaches, various technologies such as artificial intelligence (AI) and machine learning (ML) should be deployed to further aid the diagnosis, especially in endemic and epidemic situations. Computational techniques are now more at the forefront than ever, and the interest in developing such efficient technologies is continuously increasing. A comprehensive understanding of these digital technologies is needed to maintain the scientific rigour in these attempts. This would enhance the implementation of these novel technologies for malaria diagnosis. This review highlights the progression, strengths, and limitations of various computing techniques so far employed to diagnose malaria.

ROENet: A ResNet-Based Output Ensemble for Malaria Parasite Classification

Background

(1)People may be infected with an insect-borne disease (malaria) through the blood input of malaria-infected people or the bite of Anopheles mosquitoes. Doctors need a lot of time and energy to diagnose malaria, and sometimes the results are not ideal. Many researchers use CNN to classify malaria images. However, we believe that the classification performance of malaria parasites can be improved.

Methods

(2)In this paper, we propose a novel method (ROENet) to automatically classify malaria parasite on the blood smear. The backbone of ROENet is the pretrained ResNet-18. We use randomized neural networks (RNNs) as the classifier in our proposed model. Three RNNs are used in ROENet, which are random vector functional link (RVFL), Schmidt neural network (SNN), and extreme learning machine (ELM). To improve the performance of ROENet, the results of ROENet are the ensemble outputs from three RNNs.

Results

(3)We evaluate the proposed ROENet by five-fold cross-validation. The specificity, F1 score, sensitivity, and accuracy are 96.68 ± 3.81%, 95.69 ± 2.65%, 94.79 ± 3.71%, and 95.73 ± 2.63%, respectively.

Conclusions

(4)The proposed ROENet is compared with other state-of-the-art methods and provides the best results of these methods.